© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6712
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and evaluation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -0.49
     Expédié
    -0.43
    beiros
    -0.41
     dry
    -0.40
    şört
    -0.40
     Abonnez
    -0.39
    uglify
    -0.39
     hujan
    -0.38
     mainan
    -0.38
     pretty
    -0.38
    POSITIVE LOGITS
    -------
    0.50
    addCriterion
    0.49
    SpringRunner
    0.46
    Anyone
    0.45
     GK
    0.44
     Anybody
    0.44
    bbl
    0.43
    Str
    0.43
     Anyone
    0.42
    JL
    0.42
    Activations Density 0.959%

    No Known Activations